Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Robust SAC-Enabled UAV-RIS Assisted Secure MISO Systems With Untrusted EH Receivers

Hamid Reza Hashempour, Le-Nam Tran, Duy H. N. Nguyen, Hien Quoc Ngo

TL;DR

This work addresses secure downlink transmission in a UAV-mounted RIS-assisted multiuser MISO system with untrusted energy-harvesting receivers, formulating a worst-case secrecy-energy efficiency (WCSEE) objective under imperfect CSI and discrete RIS phases. A soft actor-critic (SAC) framework is proposed to jointly optimize UAV position, RIS phase shifts, and ZF power allocation, showing superior robustness to CSI uncertainty and faster convergence than baselines. As a benchmark, a tailored SCA-based solution is developed for the ideal PCSI case with continuous RIS phases, providing analytical insights and a quantitative performance reference. Results indicate the SAC approach yields notable WCSEE gains (up to ~28% over SCA and ~16% over DDPG in ideal scenarios) and robust performance across transmit-power levels and RIS sizes, underscoring the potential of learning-based strategies for complex, nonconvex UAV-RIS security problems. The work paves the way for practical secure UAV-RIS designs and motivates future extensions to multi-UAV systems and time-varying environments.

Abstract

This paper investigates secure downlink transmission in a UAV-assisted reconfigurable intelligent surface (RIS)-enabled multiuser multiple-input single-output network, where legitimate information-harvesting receivers coexist with untrusted energy-harvesting receivers (UEHRs) capable of eavesdropping. A UAV-mounted RIS provides blockage mitigation and passive beamforming, while the base station employs zero-forcing precoding for multiuser interference suppression. Due to limited feedback from UEHRs, their channel state information (CSI) is imperfect, leading to a worst-case secrecy energy efficiency (WCSEE) maximization problem. We jointly optimize the UAV horizontal position, RIS phase shifts, and transmit power allocation under both perfect and imperfect CSI, considering discrete RIS phases, UAV mobility, and energy-harvesting constraints. The resulting problem is highly nonconvex due to coupled channel geometry, robustness requirements, and discrete variables. To address this challenge, we propose a soft actor-critic (SAC)-based deep reinforcement learning framework that learns WCSEE-maximizing policies through interaction with the wireless environment. As a structured benchmark, a successive convex approximation (SCA) approach is developed for the perfect CSI case with continuous RIS phases. Simulation results show that the proposed SAC method achieves up to 28% and 16% secrecy energy efficiency gains over SCA and deep deterministic policy gradient baselines, respectively, while demonstrating superior robustness to CSI uncertainty and stable performance across varying transmit power levels and RIS sizes.

Robust SAC-Enabled UAV-RIS Assisted Secure MISO Systems With Untrusted EH Receivers

TL;DR

This work addresses secure downlink transmission in a UAV-mounted RIS-assisted multiuser MISO system with untrusted energy-harvesting receivers, formulating a worst-case secrecy-energy efficiency (WCSEE) objective under imperfect CSI and discrete RIS phases. A soft actor-critic (SAC) framework is proposed to jointly optimize UAV position, RIS phase shifts, and ZF power allocation, showing superior robustness to CSI uncertainty and faster convergence than baselines. As a benchmark, a tailored SCA-based solution is developed for the ideal PCSI case with continuous RIS phases, providing analytical insights and a quantitative performance reference. Results indicate the SAC approach yields notable WCSEE gains (up to ~28% over SCA and ~16% over DDPG in ideal scenarios) and robust performance across transmit-power levels and RIS sizes, underscoring the potential of learning-based strategies for complex, nonconvex UAV-RIS security problems. The work paves the way for practical secure UAV-RIS designs and motivates future extensions to multi-UAV systems and time-varying environments.

Abstract

This paper investigates secure downlink transmission in a UAV-assisted reconfigurable intelligent surface (RIS)-enabled multiuser multiple-input single-output network, where legitimate information-harvesting receivers coexist with untrusted energy-harvesting receivers (UEHRs) capable of eavesdropping. A UAV-mounted RIS provides blockage mitigation and passive beamforming, while the base station employs zero-forcing precoding for multiuser interference suppression. Due to limited feedback from UEHRs, their channel state information (CSI) is imperfect, leading to a worst-case secrecy energy efficiency (WCSEE) maximization problem. We jointly optimize the UAV horizontal position, RIS phase shifts, and transmit power allocation under both perfect and imperfect CSI, considering discrete RIS phases, UAV mobility, and energy-harvesting constraints. The resulting problem is highly nonconvex due to coupled channel geometry, robustness requirements, and discrete variables. To address this challenge, we propose a soft actor-critic (SAC)-based deep reinforcement learning framework that learns WCSEE-maximizing policies through interaction with the wireless environment. As a structured benchmark, a successive convex approximation (SCA) approach is developed for the perfect CSI case with continuous RIS phases. Simulation results show that the proposed SAC method achieves up to 28% and 16% secrecy energy efficiency gains over SCA and deep deterministic policy gradient baselines, respectively, while demonstrating superior robustness to CSI uncertainty and stable performance across varying transmit power levels and RIS sizes.
Paper Structure (25 sections, 3 theorems, 84 equations, 7 figures, 1 table, 5 algorithms)

This paper contains 25 sections, 3 theorems, 84 equations, 7 figures, 1 table, 5 algorithms.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. Channel Model
  4. Signal Model and ZF Beamforming
  5. Worst-Case Secrecy Rate Under CSI Uncertainty
  6. Problem Formulation
  7. SAC-Based Joint ZF Power Allocation, RIS Phase, and Location Optimization
  8. MDP Model
  9. Fundamentals of the SAC Algorithm
  10. SAC-Based Joint Optimization Framework
  11. SCA-Based Solution
  12. Power Allocation
  13. RIS Reflection Phase Optimization
  14. UAV Location Optimization
  15. Channel Separation and SINR Representation
  16. ...and 10 more sections

Key Result

Proposition 1

An affine approximation of the secrecy-related constraints in Pris_sec, for all $k\in\mathcal{K}$ and $j\in\mathcal{J}$, is given by where $\Psi^{(t)}(\mathbf{s},\rho_k;\mathbf{t}_{kk})$ is the first-order Taylor approximation of $\frac{|\mathbf{t}_{kk}^H\mathbf{s}|^2}{\rho_k}$, $\Gamma^{(t)}(x)\triangleq 2^{x^{(t-1)}}[1+\ln(2)\,(x-x^{(t-1)})]$ is the first-order Taylor approximation of $2^x$, an

Figures (7)

  • Figure 1: System model of the UAV-assisted RIS-aided secure downlink network.
  • Figure 2: SAC framework for joint power allocation, RIS phase optimization, and UAV positioning with twin critics and target Q-networks.
  • Figure 3: Convergence behavior under the ideal setting at $P_{\mathrm{max}}=10$ dBm.
  • Figure 4: SEE versus transmit power for SCA, DDPG, and the proposed SAC-based scheme.
  • Figure 5: SEE versus the number of RIS elements $M$ at $P_{\mathrm{max}}=10$ dBm for different schemes.
  • ...and 2 more figures

Theorems & Definitions (8)

  • Remark 1
  • Proposition 1
  • proof
  • Proposition 2
  • proof
  • Remark 2
  • Lemma 1
  • proof